S. Yoshimoto et al., A robust block adaptive algorithm using the average of the divided direction vectors for the observed noise, ELEC C JP 3, 84(2), 2001, pp. 47-55
Citations number
17
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Eletrical & Eletronics Engineeing
Journal title
ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE
A block orthogonal projection algorithm is proposed as a technique to balan
ce convergence speed with computational complexity. However, if the observe
d noise is convolved with the output signal of an unknown system, a shortco
ming of the block orthogonal projection algorithm is the susceptibility of
the convergence characteristics to noise. To prevent degradation of the est
imation accuracy, usually an operation is adopted to control the step gain
in the adaptive algorithm by some technique or to average the coefficient v
ectors. Sometimes the expected results are not achieved by methods employin
g these techniques. In this paper, taking the perspective of the general th
eory of an orthogonal projection algorithm represented by a Moore-Penrose g
eneralized inverse matrix, we propose an algorithm that attains excellent e
stimation accuracy by averaging over time the components constructed from t
he observed signal contained in the corrected direction vectors. This algor
ithm can be applied only under the conditions of the signal being uncorrela
ted to the observed noise and the noise having a zero mean. The convergence
characteristics are examined by a computer simulation. (C) 2000 Scripta Te
chnica, Electron Comm Jpn Pt 3, 84(2): 47-55, 2001.